Why should a researcher do a normality and outliers' assessment before hypotheses testing?
Answer
To conduct many advance statistical techniques, researchers have to presume that data provided is normal (means it's symmetrical on a bell curve) and free of outliers. In general terms, if data was plotted on a bell curve, highest number of data points would be available in the middle and the data points would reduce on either side in a proportional fashion as we move away from the middle. Normality and outliers analysis offers clarity with regard to fundamental assumption of many advance statistical techniques. Skewness and kurtosis analysis can provide some idea with regard to normality. Positive skewness values suggest clustering of data points on the low values (left hand side of the bell curve) and negative skewness values suggest clustering of datapoints on high values (right hand side of bell curve).
Positive kurtosis values suggest that datapoints have peaked (gathered in centre) with long thin tails. Kurtosis values below 0 suggest that distribution of datapoints is comparatively flat (i.e. too many cases in extreme). In a way, without normality and outlier's assessment researcher may get false results which might result in wrong conclusion and decision making.